fizzy

HIGH W007: Insecure credential handling detected in skill instructions.

• Insecure credential handling detected (high risk: 1.00). The prompt includes explicit examples and a global CLI flag (--token TOKEN, fizzy auth login TOKEN) that instruct passing API/session tokens directly on the command line and shows tokens in command/JSON examples, which would require an LLM to handle or emit secret values verbatim—creating exfiltration risk.